Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the readOnly/idempotent annotations: discloses that it makes up to 5 network fetches of public files, that it is deterministic with no LLM call, that results are cached for 24 hours, and that SPAs are detected and flagged because AI crawlers do not run JavaScript. That last caveat materially affects how an agent should interpret the result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: trigger conditions come first, then what is fetched and returned, then the framework/follow-up call, then the SPA caveat. The second sentence is long and carries three separate ideas, but almost every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates fully: it enumerates the return payload (score, seven checks with status/points/evidence grade, up to 5 ranked fixes, next step) and explains the provenance tiers A/B/C. An agent knows both what it will get and what to do next.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds the rationale for `framework` — fixes are matched to the stack and the value is reused downstream in get_fix_snippet — which the schema does not convey. The auto-detect behavior restates the schema's own note rather than adding to it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (audits a site's AI-readiness) plus concrete scope: fetches up to 5 URLs, returns a 0-100 score with seven weighted checks. The breadth is clearly distinguishable from the narrower siblings check_ai_crawlers and check_llms_txt, which cover only a subset of what is audited here.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit triggers: a user wanting to be cited by AI assistants, asking about GEO/AEO, or wondering why an assistant omits their site. It also sequences the follow-up ('then call get_fix_snippet'). It does not state when to prefer the narrower siblings (check_ai_crawlers, check_llms_txt) or any exclusion condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.